PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Predictive modeling”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 973 records · Page 54Linked to original sources
PubMed1988

A prediction model of suicide among youth.

Epidemiological relationships were studied between adolescent (ages 15 to 24 years) suicide rates and population shifts among adolescents. Suicide rates among adolescents tripled from 1956 to 1977 and have subsequently leveled off. Increases (and decreases) in adolescent suicide rates corresponded to increases (and decreases, respectively) in the proportion of adolescents in the United States. Opposite trends have been found among older age groups. Projected population fluctuations were used to predict trends in adolescent suicide rates to the year 2000: the current decrease in rates is predicted to continue until the mid-1990s. Recent data indicating a decrease in adolescent suicide rates tend to support the population model hypothesis. The data suggest that demographic variables may be of explanatory and predictive use in understanding the epidemiological trends of suicide. Early intervention and prevention strategies emerge from this model, and various social, public health, and research implications exist. However, the results must be viewed with caution because of the methodological problems inherent in using national mortality data, the possibility that other variables may account for the observed relationships, and the length of time required to test such prospective epidemiological propositions.

Adolescent↗
PubMed2005

Mortality after emergent percutaneous coronary intervention in cardiogenic shock secondary to acute myocardial infarction and usefulness of a mortality prediction model.

Although percutaneous coronary intervention (PCI) in the setting of cardiogenic shock has a high in-hospital mortality rate, it has been shown to decrease the mortality rate in certain subgroups. The identity and relative importance of variables that are predictive of in-hospital mortality rate after PCI for cardiogenic shock are uncertain. Accordingly, we examined data of >300,000 patients in the American College of Cardiology-National Cardiovascular Data Registry (ACC-NCDR) that were collected from 1998 to 2002 and evaluated the outcomes in 483 consecutive patients who underwent emergency PCI for cardiogenic shock. Patients' mean age was 65 +/- 13 years, with men predominating (61%). All underwent emergency/salvage PCI in the setting of cardiogenic shock after acute myocardial infarction. Mean left ventricular ejection fraction was 30 +/- 16%. Stents were placed in 64% of patients, and thrombolytic agents were administered in 26%. Although PCI was angiographically successful in 79% of patients, the in-hospital mortality rate was 59.4%. Length of stay after PCI was 7.2 +/- 8 days. Logistic regression using all available variables identified 6 multivariate predictors of death: age (odds ratio [OR] 2.34, 95% confidence interval [CI] 1.68 to 3.28, p <0.001) for each 10-year increment, female gender (OR 1.55, 95% CI 1.00 to 2.41, p <0.001), baseline renal insufficiency (creatinine >2.0 mg/dl; OR 4.69, 95% CI 1.96 to 11.23, p <0.001), total occlusion in the left anterior descending artery (OR 1.99, 95% confidence interval 1.28 to 3.09, p <0.01), no stent used (OR 2.55, 95% CI 1.63 to 3.96, p <0.01), and no glycoprotein IIb/IIIa inhibitor used during PCI (OR 1.96, 95% CI 1.30 to 2.98, p <0.01). In a second analysis using only variables known to the clinician at the time of initial presentation, gender, age, renal insufficiency, and total occlusion of the left anterior descending coronary artery were significant. In conclusion, analysis of patients from the ACC-NCDR who underwent emergency PCI for acute myocardial infarction in the presence of cardiogenic shock shows an in-hospital mortality rate of approximately 60% when PCI is attempted.

Age Factors↗
PubMed2005

Predictive models of molecular machines involved in Caenorhabditis elegans early embryogenesis.

Although numerous fundamental aspects of development have been uncovered through the study of individual genes and proteins, system-level models are still missing for most developmental processes. The first two cell divisions of Caenorhabditis elegans embryogenesis constitute an ideal test bed for a system-level approach. Early embryogenesis, including processes such as cell division and establishment of cellular polarity, is readily amenable to large-scale functional analysis. A first step toward a system-level understanding is to provide 'first-draft' models both of the molecular assemblies involved and of the functional connections between them. Here we show that such models can be derived from an integrated gene/protein network generated from three different types of functional relationship: protein interaction, expression profiling similarity and phenotypic profiling similarity, as estimated from detailed early embryonic RNA interference phenotypes systematically recorded for hundreds of early embryogenesis genes. The topology of the integrated network suggests that C. elegans early embryogenesis is achieved through coordination of a limited set of molecular machines. We assessed the overall predictive value of such molecular machine models by dynamic localization of ten previously uncharacterized proteins within the living embryo.

Algorithms↗
PubMed2006

Fast-track failure after cardiac surgery: development of a prediction model.

OBJECTIVE: Risk factors for unsuccessful fast-tracking of cardiac surgery patients have not been collectively defined in the literature. The aim of this study was to determine risk factors for fast-track failure and incorporate them into a predictive fast-track failure score. DESIGN: Prospective observational study. SETTING: Cardiothoracic Department of St Mary's Hospital, London. PATIENTS: Data were collected from April 2003 to April 2005 including 1,084 patients undergoing heart surgery who were admitted into the fast-track unit. INTERVENTIONS: Multifactorial logistic regression was used to develop a propensity score for estimating the likelihood of fast-track failure. MEASUREMENTS AND MAIN RESULTS: One hundred and sixty-nine patients failed fast-track management (15.6%). Independent predictors for fast-track failure were impaired left ventricular function with or without recent acute coronary syndrome (odds ratios 2.89 and 1.65 respectively), re-do operation (one, two, or more vs. none, odds ratio 1.75, 7.98), extracardiac arteriopathy (odds ratio 2.63), preoperative intra-aortic balloon pump (odds ratio 3.09), raised serum creatinine in micromol/L (120-150, >150 vs. <120, odds ratio 1.57, 11.24), and nonelective (odds ratio 3.43) and complex surgery (odds ratio 2.70). Model validation showed very good discrimination (area under the curve = 0.815) and calibration (ĉ statistic = 8.527, p = .129). CONCLUSIONS: The fast-track failure score incorporates several preoperative factors and has been successfully internally validated; after undergoing external validation and possible recalibration it may be used as a tool to facilitate planning and flow of cardiac surgery patients, based on the predicted probability of failure. Application of this score may limit fast-track failure rates and help to reduce morbidity and cost.

Aged↗
PubMed2003

Lutzomyia vectors for cutaneous leishmaniasis in Southern Brazil: ecological niche models, predicted geographic distributions, and climate change effects.

Geographic and ecological distributions of three Lutzomyia sand flies that are cutaneous leishmaniasis vectors in South America were analysed using ecological niche modelling. This new tool provides a large-scale perspective on species' geographic distributions, ecological and historical factors determining them, and their potential for change with expected environmental changes. As a first step, the ability of this technique to predict geographic distributions of the three species was tested statistically using two subsampling techniques: a random-selection technique that simulates 50% data density, and a quadrant-based technique that challenges the method to predict into broad unsampled regions. Predictivity under both test schemes was highly statistically significant. Visualisation of ecological niches provided insights into the ecological basis for distributional differences among species. Projections of potential geographic distributions across scenarios of global climate change suggested that only Lutzomyia whitmani is likely to be experiencing dramatic improvements in conditions in south-eastern Brazil, where cutaneous leishmaniasis appears to be re-emerging; Lutzomyia intermedia and Lutzomyia migonei may be seeing more subtle improvements in climatic conditions, but the implications are not straightforward. More generally, this technique offers the possibility of new views into the distributional ecology of disease, vector, and reservoir species.

Algorithms↗
PubMed2004

Using path sampling to build better Markovian state models: predicting the folding rate and mechanism of a tryptophan zipper beta hairpin.

We propose an efficient method for the prediction of protein folding rate constants and mechanisms. We use molecular dynamics simulation data to build Markovian state models (MSMs), discrete representations of the pathways sampled. Using these MSMs, we can quickly calculate the folding probability (P(fold)) and mean first passage time of all the sampled points. In addition, we provide techniques for evaluating these values under perturbed conditions without expensive recomputations. To demonstrate this method on a challenging system, we apply these techniques to a two-dimensional model energy landscape and the folding of a tryptophan zipper beta hairpin.

Computational Biology↗
PubMed1998

Predicting the distribution of synaptic strengths and cell firing correlations in a self-organizing, sequence prediction model.

This article investigates the synaptic weight distribution of a self-supervised, sparse, and randomly connected recurrent network inspired by hippocampal region CA3. This network solves nontrivial sequence prediction problems by creating, on a neuron-by-neuron basis, special patterns of cell firing called local context units. These specialized patterns of cell firing--possibly an analog of hippocampal place cells--allow accurate prediction of the statistical distribution of synaptic weights, and this distribution is not at all gaussian. Aside from the majority of synapses that are, at least functionally, lost due to synaptic depression, the distribution is approximately uniform. Unexpectedly, this result is relatively independent of the input environment, and the uniform distribution of synaptic weights can be approximately parameterized based solely on the average activity level. Next, the results are generalized to other cell firing types (frequency codes and stochastic firing) and place cell-like firing distributions. Finally, we note that our predictions concerning the synaptic strength distribution can be extended to the distribution of correlated cell firings. Recent published neurophysiological results are consistent with this extension.

Electrophysiology↗
PubMed1989

Monte Carlo modeling of light propagation in highly scattering tissue--I: Model predictions and comparison with diffusion theory.

Using optical interaction coefficients typical of mammalian soft tissues in the red and near infrared regions of the spectrum, calculations of fluence-depth distributions, effective penetration depths and diffuse reflectance from two models of radiative transfer, diffusion theory, and Monte Carlo simulation are compared for a semi-infinite medium. The predictions from diffusion theory are shown to be increasingly inaccurate as the albedo tends to zero and/or the average cosine of scatter tends to unity.

Light↗
PubMed2005

A multicellular systems biology model predicts epidermal morphology, kinetics and Ca2+ flow.

MOTIVATION: Systems biology is currently focused on integrating intracellular networks, although clinically, diseases are largely defined by their histological features. For example, no computational model can simulate today the formation of a horizontally layered epidermis. Since the epidermis is the most complex structured epithelial tissue, systems biology models could yield important insights in epithelial tissue, in which most of all human cancers arise. RESULTS: We describe the algorithms of a system, capable of simulating the tissue homeostasis in human epidermis leading to a horizontally layered tissue with cells of different differentiation stages. The system predicts epidermal morphology, tissue kinetics and 2D flow of Ca2+ ions. Predicted properties of an epidermis with a healthy and a disturbed barrier are compared with the literature. The system closely mimics the respecting physiological situations. AVAILABILITY: Additional information and films of the simulation are available at the website. Source code is available on request. http://www.zbh.uni-hamburg.de/research/ESB/index.php CONTACT: grabe@zbh.uni-hamburg.de

Algorithms↗
PubMed2004

Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma.

BACKGROUND: Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease. RESULTS: To predict development of childhood allergic asthma (CAA) and select susceptible SNPs, we used an ANN with a parameter decreasing method (PDM) to analyze 25 SNPs of 17 genes in 344 Japanese people, and select 10 susceptible SNPs of CAA. The accuracy of the ANN model with 10 SNPs was 97.7% for learning data and 74.4% for evaluation data. Important combinations were determined by effective combination value (ECV) defined in the present paper. Effective 2-SNP or 3-SNP combinations were found to be concentrated among the 10 selected SNPs. CONCLUSION: ANN can reliably select SNP combinations that are associated with CAA. Thus, the ANN can be used to characterize development of complex diseases caused by multiple factors. This is the first report of automatic selection of SNPs related to development of multifactorial disease from SNP data of more than 300 patients.

Alleles↗
PubMed2007

Structure-based maximal affinity model predicts small-molecule druggability.

Lead generation is a major hurdle in small-molecule drug discovery, with an estimated 60% of projects failing from lack of lead matter or difficulty in optimizing leads for drug-like properties. It would be valuable to identify these less-druggable targets before incurring substantial expenditure and effort. Here we show that a model-based approach using basic biophysical principles yields good prediction of druggability based solely on the crystal structure of the target binding site. We quantitatively estimate the maximal affinity achievable by a drug-like molecule, and we show that these calculated values correlate with drug discovery outcomes. We experimentally test two predictions using high-throughput screening of a diverse compound collection. The collective results highlight the utility of our approach as well as strategies for tackling difficult targets.

Algorithms↗
PubMed1998

A model predicting individual shoulder muscle forces based on relationship between electromyographic and 3D external forces in static position.

To study the potentiality for developing an EMG-based model for the human shoulder, mapping of relations between static hand forces and electromyographic (EMG) activity of 13 shoulder muscles, were performed. The procedure was to perform by the hands slowly varying isometric forces up to 20% maximum voluntary force in the three-dimensional space. By combining these data with literature values on muscle physiological cross-sectional area and moment arm data, an EMG-based model was developed for estimating muscle forces in the glenohumeral joint. The model was validated for one standardized position by comparing joint moment, calculated from EMG by using the model, with moments from the external force. The highest correlation between these moments was found assuming a linear EMG/force calibration at low force level (< 20% MVC), giving correlations from 0.65 to 0.95 for the abduction/adduction moment and from 0.70 to 0.93 for the flexion/extension moment, for the six subjects. Moments calculated from EMG were for most subjects somewhat lower than the moments from the external force; the mean residual error ranged from 1.6 to 9.9 Nm. Taking this into account, the results can be used for assessment of muscle forces based on recordings of external forces at the hands during submaximal static work tasks without substantially elevated arms.

Adult↗